Share Email Print
cover

Proceedings Paper

Estimating psycho-physiological state of a human by speech analysis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Adverse effects of intoxication, fatigue and boredom could degrade performance of highly trained operators of complex technical systems with potentially catastrophic consequences. Existing physiological fitness for duty tests are time consuming, costly, invasive, and highly unpopular. Known non-physiological tests constitute a secondary task and interfere with the busy workload of the tested operator. Various attempts to assess the current status of the operator by processing of "normal operational data" often lead to excessive amount of computations, poorly justified metrics, and ambiguity of results. At the same time, speech analysis presents a natural, non-invasive approach based upon well-established efficient data processing. In addition, it supports both behavioral and physiological biometric. This paper presents an approach facilitating robust speech analysis/understanding process in spite of natural speech variability and background noise. Automatic speech recognition is suggested as a technique for the detection of changes in the psycho-physiological state of a human that typically manifest themselves by changes of characteristics of voice tract and semantic-syntactic connectivity of conversation. Preliminary tests have confirmed that the statistically significant correlation between the error rate of automatic speech recognition and the extent of alcohol intoxication does exist. In addition, the obtained data allowed exploring some interesting correlations and establishing some quantitative models. It is proposed to utilize this approach as a part of fitness for duty test and compare its efficiency with analyses of iris, face geometry, thermography and other popular non-invasive biometric techniques.

Paper Details

Date Published: 23 May 2005
PDF: 12 pages
Proc. SPIE 5797, Biomonitoring for Physiological and Cognitive Performance during Military Operations, (23 May 2005); doi: 10.1117/12.602765
Show Author Affiliations
A. Leonidovich Ronzhin, St. Petersburg Institute for Informatics and Automation (Russia)


Published in SPIE Proceedings Vol. 5797:
Biomonitoring for Physiological and Cognitive Performance during Military Operations
John A. Caldwell; Nancy Jo Wesensten, Editor(s)

© SPIE. Terms of Use
Back to Top